Models & ArchitectureFeaturedUpdated 2026-10-24
Diffusion Model
A generative model that turns random noise into images, video or audio through iterative denoising.
#扩散#图像生成#视频生成
In plain language
Diffusion powers image tools such as Midjourney, Stable Diffusion and FLUX. Quality depends on prompts, sampling steps, models and LoRAs. Video diffusion adds the time dimension to denoising.
Example
Start from pure noise and denoise over 20-50 steps to get a poster.
Recommended tools
Related terms
Models & Architecture
ControlNet
An add-on that gives diffusion models structural control from pose, edges, depth and more.
3 related terms
Models & Architecture
Latent Space
A compressed high-dimensional representation space where diffusion often operates.
3 related terms
ApplicationsFeatured
Text-to-Video
Generating video clips from text descriptions.
3 related terms
Applications
Agentic Workflow
Breaking a task into steps planned by AI, executed by tools and reviewed by humans.
3 related terms